
# Libraries to help with reading and manipulating data
import numpy as np
import pandas as pd

# Libraries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns

sns.set_theme(style='darkgrid')

# Removes the limit for the number of displayed columns
pd.set_option("display.max_columns", None)
# Sets the limit for the number of displayed rows
pd.set_option("display.max_rows", 200)

# to scale the data using z-score
from sklearn.preprocessing import StandardScaler

# to compute distances
from scipy.spatial.distance import cdist, pdist

# to perform k-means clustering and compute silhouette scores
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score

# to visualize the elbow curve and silhouette scores
from yellowbrick.cluster import KElbowVisualizer, SilhouetteVisualizer

# to perform hierarchical clustering, compute cophenetic correlation, and create dendrograms
from sklearn.cluster import AgglomerativeClustering
from scipy.cluster.hierarchy import dendrogram, linkage, cophenet

# to suppress warnings
import warnings
warnings.filterwarnings("ignore")


data = pd.read_csv('/content/stock_data.csv')


# to check the shape of the data
data.shape

(340, 15)


# to view a sample of the data
data.sample(n=10, random_state=1)


# to check column data types
data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 340 entries, 0 to 339
Data columns (total 15 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   Ticker Symbol                 340 non-null    object 
 1   Security                      340 non-null    object 
 2   GICS Sector                   340 non-null    object 
 3   GICS Sub Industry             340 non-null    object 
 4   Current Price                 340 non-null    float64
 5   Price Change                  340 non-null    float64
 6   Volatility                    340 non-null    float64
 7   ROE                           340 non-null    int64  
 8   Cash Ratio                    340 non-null    int64  
 9   Net Cash Flow                 340 non-null    int64  
 10  Net Income                    340 non-null    int64  
 11  Earnings Per Share            340 non-null    float64
 12  Estimated Shares Outstanding  340 non-null    float64
 13  P/E Ratio                     340 non-null    float64
 14  P/B Ratio                     340 non-null    float64
dtypes: float64(7), int64(4), object(4)
memory usage: 40.0+ KB


# to copy data so original data is unchanged
stocks = data.copy()


# to check for duplicated data
stocks.duplicated().sum()

0


# to check for missing values in the data
stocks.isnull().sum()

Ticker Symbol                   0
Security                        0
GICS Sector                     0
GICS Sub Industry               0
Current Price                   0
Price Change                    0
Volatility                      0
ROE                             0
Cash Ratio                      0
Net Cash Flow                   0
Net Income                      0
Earnings Per Share              0
Estimated Shares Outstanding    0
P/E Ratio                       0
P/B Ratio                       0
dtype: int64


# to view the statistical summary of the data
stocks.describe(include='all').T


# function to plot a boxplot and a histogram along the same scale.


def histogram_boxplot(df, feature, figsize=(12, 7), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (12,7))
    kde: whether to the show density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.25, 0.75)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=df, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(
        data=df, x=feature, kde=kde, ax=ax_hist2, bins=bins, palette="winter"
    ) if bins else sns.histplot(
        data=df, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        df[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        df[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram


# to view a histogram boxplot of Current Price
histogram_boxplot(stocks, 'Current Price')


# to view a histogram boxplot of Price Change
histogram_boxplot(stocks, 'Price Change')


# to view a histogram boxplot of Volatility
histogram_boxplot(stocks, 'Volatility')


# to view a histogram boxplot of ROE
histogram_boxplot(stocks, 'ROE')


# to view a histogram boxplot of Cash Ratio
histogram_boxplot(stocks, 'Cash Ratio')


# to view a histogram boxplot of Net Cash Flow
histogram_boxplot(stocks, 'Net Cash Flow')


# to view a histogram boxplot of Net Income
histogram_boxplot(stocks, 'Net Income')


# to view a histogram boxplot of Earnings Per Share
histogram_boxplot(stocks, 'Earnings Per Share')


# to view a histogram boxplot of Estimated Shares Outstanding
histogram_boxplot(stocks, 'Current Price')


# to view a histogram boxplot of P/E Ratio
histogram_boxplot(stocks, 'P/E Ratio')


# to view a histogram boxplot of P/B Ratio
histogram_boxplot(stocks, 'P/B Ratio')


# function to create labeled barplots


def labeled_barplot(df, feature, perc=False, n=None):
    """
    Barplot with percentage at the top

    data: dataframe
    feature: dataframe column
    perc: whether to display percentages instead of count (default is False)
    n: displays the top n category levels (default is None, i.e., display all levels)
    """

    total = len(df[feature])  # length of the column
    count = df[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 1, 5))
    else:
        plt.figure(figsize=(n + 1, 5))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=df,
        x=feature,
        palette="Paired",
        order=df[feature].value_counts().index[:n].sort_values(),
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            )  # percentage of each class of the category
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  # annotate the percentage

    plt.show()  # show the plot


# to view labeled barplot for GICS Sector
labeled_barplot(stocks, 'GICS Sector', perc=True)


# to view labeled barplot for GICS Sub Industry
labeled_barplot(stocks, 'GICS Sub Industry', perc=True)


# to create a lineplot of current price and security
plt.figure(figsize=(100,5))
sns.lineplot(data=stocks, x='Security', y='Current Price')
plt.xticks(rotation=90)
plt.show()


# to create a barplot of GICS Sector and Price Change
plt.figure(figsize=(15,8))
sns.barplot(data=stocks, x='GICS Sector', y='Price Change', ci=False)
plt.xticks(rotation=90)
plt.show()


# correlation check
plt.figure(figsize=(15, 7))
sns.heatmap(
    stocks.corr(), annot=True, vmin=-1, vmax=1, fmt=".2f", cmap="Spectral"
)
plt.show()


# to view Cash Ratios by GICS Sector as a barplot
plt.figure(figsize=(15,8))
sns.barplot(data=stocks, x='GICS Sector', y='Cash Ratio', ci=False)
plt.xticks(rotation=90)
plt.show()


# to view P/E Ratios by GICS Sector as a barplot
plt.figure(figsize=(15,8))
sns.barplot(data=stocks, x='GICS Sector', y='P/E Ratio', ci=False)
plt.xticks(rotation=90)
plt.show()


# to check for duplicated data
stocks.duplicated().sum()

0


# to check for missing values
stocks.isnull().sum()

Ticker Symbol                   0
Security                        0
GICS Sector                     0
GICS Sub Industry               0
Current Price                   0
Price Change                    0
Volatility                      0
ROE                             0
Cash Ratio                      0
Net Cash Flow                   0
Net Income                      0
Earnings Per Share              0
Estimated Shares Outstanding    0
P/E Ratio                       0
P/B Ratio                       0
dtype: int64


# to plot the boxplots of all numerical columns to check for outliers
plt.figure(figsize=(15, 12))

numeric_columns = stocks.select_dtypes(include=np.number).columns.tolist()

for i, variable in enumerate(numeric_columns):
    plt.subplot(3, 4, i + 1)
    plt.boxplot(stocks[variable], whis=1.5)
    plt.tight_layout()
    plt.title(variable)

plt.show()


# scaling the data before clustering
scaler = StandardScaler()
subset = stocks[numeric_columns].copy()
subset_scaled = scaler.fit_transform(subset)


# creating a dataframe of the scaled data
subset_scaled_df = pd.DataFrame(subset_scaled, columns=subset.columns)


k_means_df = subset_scaled_df.copy()


clusters = range(1, 15)
meanDistortions = []

for k in clusters:
    model = KMeans(n_clusters=k, random_state=1)
    model.fit(subset_scaled_df)
    prediction = model.predict(k_means_df)
    distortion = (
        sum(np.min(cdist(k_means_df, model.cluster_centers_, "euclidean"), axis=1))
        / k_means_df.shape[0]
    )

    meanDistortions.append(distortion)

    print("Number of Clusters:", k, "\tAverage Distortion:", distortion)

plt.plot(clusters, meanDistortions, "bx-")
plt.xlabel("k")
plt.ylabel("Average Distortion")
plt.title("Selecting k with the Elbow Method", fontsize=20)
plt.show()

Number of Clusters: 1 	Average Distortion: 2.5425069919221697
Number of Clusters: 2 	Average Distortion: 2.382318498894466
Number of Clusters: 3 	Average Distortion: 2.2692367155390745
Number of Clusters: 4 	Average Distortion: 2.1745559827866363
Number of Clusters: 5 	Average Distortion: 2.128799332840716
Number of Clusters: 6 	Average Distortion: 2.080400099226289
Number of Clusters: 7 	Average Distortion: 2.0289794220177395
Number of Clusters: 8 	Average Distortion: 1.964144163389972
Number of Clusters: 9 	Average Distortion: 1.9221492045198068
Number of Clusters: 10 	Average Distortion: 1.8513913649973124
Number of Clusters: 11 	Average Distortion: 1.8024134734578485
Number of Clusters: 12 	Average Distortion: 1.7900931879652673
Number of Clusters: 13 	Average Distortion: 1.7417609203336912
Number of Clusters: 14 	Average Distortion: 1.673559857259703


model = KMeans(random_state=1)
visualizer = KElbowVisualizer(model, k=(1, 15), timings=True)
visualizer.fit(k_means_df)  # fit the data to the visualizer
visualizer.show()  # finalize and render figure

<Axes: title={'center': 'Distortion Score Elbow for KMeans Clustering'}, xlabel='k', ylabel='distortion score'>


sil_score = []
cluster_list = range(2, 15)
for n_clusters in cluster_list:
    clusterer = KMeans(n_clusters=n_clusters, random_state=1)
    preds = clusterer.fit_predict((subset_scaled_df))
    score = silhouette_score(k_means_df, preds)
    sil_score.append(score)
    print("For n_clusters = {}, the silhouette score is {})".format(n_clusters, score))

plt.plot(cluster_list, sil_score)
plt.show()

For n_clusters = 2, the silhouette score is 0.43969639509980457)
For n_clusters = 3, the silhouette score is 0.4644405674779404)
For n_clusters = 4, the silhouette score is 0.4577225970476733)
For n_clusters = 5, the silhouette score is 0.43228336443659804)
For n_clusters = 6, the silhouette score is 0.4005422737213617)
For n_clusters = 7, the silhouette score is 0.3976335364987305)
For n_clusters = 8, the silhouette score is 0.40278401969450467)
For n_clusters = 9, the silhouette score is 0.3778585981433699)
For n_clusters = 10, the silhouette score is 0.13458938329968687)
For n_clusters = 11, the silhouette score is 0.1421832155528444)
For n_clusters = 12, the silhouette score is 0.2044669621527429)
For n_clusters = 13, the silhouette score is 0.23424874810104204)
For n_clusters = 14, the silhouette score is 0.12102526472829901)


model = KMeans(random_state=1)
visualizer = KElbowVisualizer(model, k=(2, 15), metric="silhouette", timings=True)
visualizer.fit(k_means_df)  # fit the data to the visualizer
visualizer.show()  # finalize and render figure

<Axes: title={'center': 'Silhouette Score Elbow for KMeans Clustering'}, xlabel='k', ylabel='silhouette score'>


# finding optimal no. of clusters with silhouette coefficients
visualizer = SilhouetteVisualizer(KMeans(10, random_state=1))
visualizer.fit(k_means_df)
visualizer.show()

<Axes: title={'center': 'Silhouette Plot of KMeans Clustering for 340 Samples in 10 Centers'}, xlabel='silhouette coefficient values', ylabel='cluster label'>


# final K-means model
kmeans = KMeans(n_clusters= 10, random_state=1)
kmeans.fit(k_means_df)

KMeans(n_clusters=10, random_state=1)

KMeans(n_clusters=10, random_state=1)


# creating a copy of the original data
stocks1 = stocks.copy()

# adding kmeans cluster labels to the original and scaled dataframes
k_means_df['KM_segments'] = kmeans.labels_
stocks1['KM_segments'] = kmeans.labels_


km_cluster_profile = stocks1.groupby('KM_segments').mean()


km_cluster_profile['count_in_each_segment'] = (
    stocks1.groupby('KM_segments')["Security"].count().values
)


km_cluster_profile.style.highlight_max(color="lightblue", axis=0)


# to print the companies in each cluster
for cl in stocks1["KM_segments"].unique():
    print("In cluster {}, the following companies are present:".format(cl))
    print(stocks1[stocks1["KM_segments"] == cl]["Security"].unique())
    print('-' * 100, '\n')

In cluster 0, the following companies are present:
['American Airlines Group' 'AbbVie' 'Abbott Laboratories'
 'Adobe Systems Inc' 'American International Group, Inc.' 'Albemarle Corp'
 'Applied Materials Inc' 'Arconic Inc' 'Activision Blizzard' 'Broadcom'
 'Boeing Company' 'Baxter International Inc.'
 'The Bank of New York Mellon Corp.' 'Ball Corp' 'Bristol-Myers Squibb'
 'Boston Scientific' 'BorgWarner' 'Caterpillar Inc.'
 'Citizens Financial Group' 'Centene Corporation' 'Citrix Systems'
 'Chevron Corp.' 'Delta Air Lines' 'Du Pont (E.I.)' 'Deere & Co.'
 'Quest Diagnostics' 'Delphi Automotive' 'Digital Realty Trust'
 'Dr Pepper Snapple Group' 'E*Trade' 'Fastenal Co'
 'Fortune Brands Home & Security' 'Fluor Corp.' 'FMC Corporation'
 'Gilead Sciences' 'Corning Inc.' 'General Motors' 'Garmin Ltd.'
 'Goodyear Tire & Rubber' 'Huntington Bancshares' "Honeywell Int'l Inc."
 'HP Inc.' 'Hormel Foods Corp.' 'Henry Schein' 'Host Hotels & Resorts'
 'Intl Flavors & Fragrances' 'Interpublic Group' 'Illinois Tool Works'
 'Invesco Ltd.' 'Jacobs Engineering Group' 'Juniper Networks'
 'Kimco Realty' 'Laboratory Corp. of America Holding'
 'L-3 Communications Holdings' 'Southwest Airlines'
 'Level 3 Communications' 'LyondellBasell' 'Mastercard Inc.' 'Masco Corp.'
 'Mattel Inc.' 'Mondelez International' 'Mead Johnson' 'Altria Group Inc'
 'Marathon Petroleum' 'Merck & Co.' 'Mylan N.V.' 'Navient'
 'Norfolk Southern Corp.' 'Nucor Corp.' 'Newell Brands'
 'Philip Morris International' 'PPG Industries' 'Phillips 66' 'PayPal'
 'Roper Industries' 'Charles Schwab Corporation' 'Sherwin-Williams'
 'Scripps Networks Interactive Inc.' 'SunTrust Banks' 'Tegna, Inc.'
 'The Travelers Companies Inc.' 'Tyson Foods' 'Tesoro Petroleum Co.'
 'Total System Services' 'Texas Instruments' 'Varian Medical Systems'
 'Valero Energy' 'Vulcan Materials' 'Verisign Inc.' 'Weyerhaeuser Corp.'
 'Dentsply Sirona' 'Xerox Corp.' 'Xylem Inc.' 'Zoetis']
---------------------------------------------------------------------------------------------------- 

In cluster 6, the following companies are present:
['Analog Devices, Inc.' 'Amgen Inc' 'Celgene Corp.' 'eBay Inc.'
 'Edwards Lifesciences' 'Facebook' 'First Solar Inc'
 'Frontier Communications' 'Halliburton Co.' "McDonald's Corp."
 'Monster Beverage' 'Newmont Mining Corp. (Hldg. Co.)'
 'Skyworks Solutions' 'TripAdvisor' 'Vertex Pharmaceuticals Inc'
 'Waters Corporation' 'Wynn Resorts Ltd' 'Yahoo Inc.']
---------------------------------------------------------------------------------------------------- 

In cluster 1, the following companies are present:
['Archer-Daniels-Midland Co' 'Ameren Corp' 'American Electric Power'
 'AFLAC Inc' 'Apartment Investment & Mgmt' 'Assurant Inc'
 'Arthur J. Gallagher & Co.' 'Akamai Technologies Inc'
 'Alaska Air Group Inc' 'Allstate Corp' 'AMETEK Inc'
 'Affiliated Managers Group Inc' 'Ameriprise Financial'
 'American Tower Corp A' 'AutoNation Inc' 'Anthem Inc.' 'Aon plc'
 'Amphenol Corp' 'AvalonBay Communities, Inc.'
 'American Water Works Company Inc' 'American Express Co'
 'BB&T Corporation' 'Bard (C.R.) Inc.' 'Boston Properties' 'Chubb Limited'
 'CBRE Group' 'Crown Castle International Corp.' 'Carnival Corp.'
 'CF Industries Holdings Inc' 'Church & Dwight' 'C. H. Robinson Worldwide'
 'CIGNA Corp.' 'Cincinnati Financial' 'Comerica Inc.' 'CME Group Inc.'
 'Cummins Inc.' 'CMS Energy' 'CenterPoint Energy' 'Capital One Financial'
 'The Cooper Companies' 'CSX Corp.' 'CenturyLink Inc'
 'Cognizant Technology Solutions' 'CVS Health' 'Dominion Resources'
 'Discover Financial Services' 'Danaher Corp.' 'The Walt Disney Company'
 'Discovery Communications-A' 'Discovery Communications-C'
 'Dun & Bradstreet' 'Dover Corp.' 'Duke Energy' 'DaVita Inc.'
 'Ecolab Inc.' 'Consolidated Edison' 'Equifax Inc.' "Edison Int'l"
 'Eastman Chemical' 'Equity Residential' 'Eversource Energy'
 'Essex Property Trust, Inc.' 'Eaton Corporation' 'Entergy Corp.'
 'Exelon Corp.' "Expeditors Int'l" 'Expedia Inc.' 'Extra Space Storage'
 'FirstEnergy Corp' 'Fidelity National Information Services' 'Fiserv Inc'
 'FLIR Systems' 'Flowserve Corporation' 'Federal Realty Investment Trust'
 'General Dynamics' 'General Growth Properties Inc.' 'Genuine Parts'
 'Grainger (W.W.) Inc.' 'Hasbro Inc.' 'HCA Holdings' 'Welltower Inc.'
 'HCP Inc.' 'Hartford Financial Svc.Gp.' 'Harley-Davidson'
 'The Hershey Company' 'Humana Inc.' 'International Business Machines'
 'IDEXX Laboratories' 'International Paper' 'Iron Mountain Incorporated'
 'J. B. Hunt Transport Services' 'Kansas City Southern' 'Leggett & Platt'
 'Lennar Corp.' 'LKQ Corporation' 'Lilly (Eli) & Co.'
 'Lockheed Martin Corp.' 'Alliant Energy Corp' 'Leucadia National Corp.'
 'Mid-America Apartments' 'Macerich' "Marriott Int'l." "Moody's Corp"
 'MetLife Inc.' 'Mohawk Industries' 'McCormick & Co.'
 'Martin Marietta Materials' 'Marsh & McLennan' '3M Company'
 'M&T Bank Corp.' 'NASDAQ OMX Group' 'NextEra Energy' 'Nielsen Holdings'
 'Northern Trust Corp.' 'Realty Income Corporation' 'Omnicom Group'
 "O'Reilly Automotive" "People's United Financial" 'Pitney-Bowes'
 'PACCAR Inc.' 'PG&E Corp.' 'Public Serv. Enterprise Inc.' 'PepsiCo Inc.'
 'Principal Financial Group' 'Procter & Gamble' 'Progressive Corp.'
 'Pulte Homes Inc.' 'PNC Financial Services' 'Pentair Ltd.'
 'Pinnacle West Capital' 'PPL Corp.' 'Prudential Financial' 'Praxair Inc.'
 'Ryder System' 'Royal Caribbean Cruises Ltd' 'Robert Half International'
 'Republic Services Inc' 'SCANA Corp' 'Sealed Air' 'SL Green Realty'
 'Southern Co.' 'Simon Property Group Inc' 'Stericycle Inc'
 'Sempra Energy' 'State Street Corp.' 'Synchrony Financial'
 'Stryker Corp.' 'Molson Coors Brewing Company' 'Torchmark Corp.'
 'Thermo Fisher Scientific' 'Tractor Supply Company' 'Under Armour'
 'United Continental Holdings' 'UDR Inc' 'Universal Health Services, Inc.'
 'United Health Group Inc.' 'Unum Group' 'Union Pacific'
 'United Parcel Service' 'United Technologies' 'Vornado Realty Trust'
 'Verisk Analytics' 'Ventas Inc' 'Wec Energy Group Inc' 'Whirlpool Corp.'
 'Waste Management Inc.' 'Western Union Co' 'Wyndham Worldwide'
 'Xcel Energy Inc' 'XL Capital' 'Yum! Brands Inc' 'Zimmer Biomet Holdings'
 'Zions Bancorp']
---------------------------------------------------------------------------------------------------- 

In cluster 7, the following companies are present:
['Alliance Data Systems' 'BIOGEN IDEC Inc.' 'Chipotle Mexican Grill'
 'Equinix' 'Intuitive Surgical Inc.' 'Mettler Toledo' 'Priceline.com Inc'
 'Regeneron']
---------------------------------------------------------------------------------------------------- 

In cluster 4, the following companies are present:
['Allegion' 'Charter Communications' 'Colgate-Palmolive' 'Kimberly-Clark'
 'S&P Global, Inc.']
---------------------------------------------------------------------------------------------------- 

In cluster 3, the following companies are present:
['Alexion Pharmaceuticals' 'Amazon.com Inc' 'Netflix Inc.']
---------------------------------------------------------------------------------------------------- 

In cluster 8, the following companies are present:
['Apache Corporation' 'Chesapeake Energy']
---------------------------------------------------------------------------------------------------- 

In cluster 9, the following companies are present:
['Anadarko Petroleum Corp' 'Baker Hughes Inc' 'Cabot Oil & Gas'
 'Concho Resources' 'Devon Energy Corp.' 'EOG Resources' 'EQT Corporation'
 'Freeport-McMoran Cp & Gld' 'Hess Corporation'
 'Hewlett Packard Enterprise' 'Kinder Morgan' 'The Mosaic Company'
 'Marathon Oil Corp.' 'Murphy Oil' 'Noble Energy Inc'
 'Newfield Exploration Co' 'National Oilwell Varco Inc.' 'ONEOK'
 'Occidental Petroleum' 'Quanta Services Inc.' 'Range Resources Corp.'
 'Spectra Energy Corp.' 'Southwestern Energy' 'Teradata Corp.'
 'Williams Cos.' 'Cimarex Energy']
---------------------------------------------------------------------------------------------------- 

In cluster 5, the following companies are present:
['Bank of America Corp' 'Intel Corp.']
---------------------------------------------------------------------------------------------------- 

In cluster 2, the following companies are present:
['Citigroup Inc.' 'Ford Motor' 'JPMorgan Chase & Co.' 'Coca Cola Company'
 'Pfizer Inc.' 'AT&T Inc' 'Verizon Communications' 'Wells Fargo'
 'Exxon Mobil Corp.']
----------------------------------------------------------------------------------------------------


stocks1.groupby(["KM_segments", "GICS Sector"])['Security'].count()

KM_segments  GICS Sector                
0            Consumer Discretionary         10
             Consumer Staples                7
             Energy                          5
             Financials                     10
             Health Care                    15
             Industrials                    18
             Information Technology         14
             Materials                      10
             Real Estate                     4
             Telecommunications Services     1
1            Consumer Discretionary         22
             Consumer Staples                8
             Financials                     34
             Health Care                    14
             Industrials                    33
             Information Technology          8
             Materials                       7
             Real Estate                    22
             Telecommunications Services     1
             Utilities                      24
2            Consumer Discretionary          1
             Consumer Staples                1
             Energy                          1
             Financials                      3
             Health Care                     1
             Telecommunications Services     2
3            Consumer Discretionary          1
             Health Care                     1
             Information Technology          1
4            Consumer Discretionary          1
             Consumer Staples                2
             Financials                      1
             Industrials                     1
5            Financials                      1
             Information Technology          1
6            Consumer Discretionary          3
             Consumer Staples                1
             Energy                          1
             Health Care                     5
             Information Technology          6
             Materials                       1
             Telecommunications Services     1
7            Consumer Discretionary          2
             Health Care                     4
             Information Technology          1
             Real Estate                     1
8            Energy                          2
9            Energy                         21
             Industrials                     1
             Information Technology          2
             Materials                       2
Name: Security, dtype: int64


plt.figure(figsize=(20, 20))
plt.suptitle("Boxplot of numerical variables for each cluster")

# selecting numerical columns
num_col = stocks.select_dtypes(include=np.number).columns.tolist()

for i, variable in enumerate(num_col):
    plt.subplot(3, 4, i + 1)
    sns.boxplot(data=stocks1, x="KM_segments", y=variable)

plt.tight_layout(pad=2.0)


hc_df = subset_scaled_df.copy()


# list of distance metrics
distance_metrics = ["euclidean", "chebyshev", "mahalanobis", "cityblock"]

# list of linkage methods
linkage_methods = ["single", "complete", "average", "weighted"]

high_cophenet_corr = 0
high_dm_lm = [0, 0]

for dm in distance_metrics:
    for lm in linkage_methods:
        Z = linkage(hc_df, metric=dm, method=lm)
        c, coph_dists = cophenet(Z, pdist(hc_df))
        print(
            "Cophenetic correlation for {} distance and {} linkage is {}.".format(
                dm.capitalize(), lm, c
            )
        )
        if high_cophenet_corr < c:
            high_cophenet_corr = c
            high_dm_lm[0] = dm
            high_dm_lm[1] = lm

# printing the combination of distance metric and linkage method with the highest cophenetic correlation
print('*'*100)
print(
    "Highest cophenetic correlation is {}, which is obtained with {} distance and {} linkage.".format(
        high_cophenet_corr, high_dm_lm[0].capitalize(), high_dm_lm[1]
    )
)

Cophenetic correlation for Euclidean distance and single linkage is 0.9232271494002922.
Cophenetic correlation for Euclidean distance and complete linkage is 0.7873280186580672.
Cophenetic correlation for Euclidean distance and average linkage is 0.9422540609560814.
Cophenetic correlation for Euclidean distance and weighted linkage is 0.8693784298129404.
Cophenetic correlation for Chebyshev distance and single linkage is 0.9062538164750717.
Cophenetic correlation for Chebyshev distance and complete linkage is 0.598891419111242.
Cophenetic correlation for Chebyshev distance and average linkage is 0.9338265528030499.
Cophenetic correlation for Chebyshev distance and weighted linkage is 0.9127355892367.
Cophenetic correlation for Mahalanobis distance and single linkage is 0.925919553052459.
Cophenetic correlation for Mahalanobis distance and complete linkage is 0.7925307202850002.
Cophenetic correlation for Mahalanobis distance and average linkage is 0.9247324030159736.
Cophenetic correlation for Mahalanobis distance and weighted linkage is 0.8708317490180428.
Cophenetic correlation for Cityblock distance and single linkage is 0.9334186366528574.
Cophenetic correlation for Cityblock distance and complete linkage is 0.7375328863205818.
Cophenetic correlation for Cityblock distance and average linkage is 0.9302145048594667.
Cophenetic correlation for Cityblock distance and weighted linkage is 0.731045513520281.
****************************************************************************************************
Highest cophenetic correlation is 0.9422540609560814, which is obtained with Euclidean distance and average linkage.


# printing the combination of distance metric and linkage method with the highest cophenetic correlation
print(
    "Highest cophenetic correlation is {}, which is obtained with {} distance and {} linkage.".format(
        high_cophenet_corr, high_dm_lm[0].capitalize(), high_dm_lm[1]
    )
)

Highest cophenetic correlation is 0.9422540609560814, which is obtained with Euclidean distance and average linkage.


# list of linkage methods
linkage_methods = ["single", "complete", "average", "centroid", "ward", "weighted"]

high_cophenet_corr = 0
high_dm_lm = [0, 0]

for lm in linkage_methods:
    Z = linkage(subset_scaled_df, metric="euclidean", method=lm)
    c, coph_dists = cophenet(Z, pdist(subset_scaled_df))
    print("Cophenetic correlation for {} linkage is {}.".format(lm, c))
    if high_cophenet_corr < c:
        high_cophenet_corr = c
        high_dm_lm[0] = "euclidean"
        high_dm_lm[1] = lm

Cophenetic correlation for single linkage is 0.9232271494002922.
Cophenetic correlation for complete linkage is 0.7873280186580672.
Cophenetic correlation for average linkage is 0.9422540609560814.
Cophenetic correlation for centroid linkage is 0.9314012446828154.
Cophenetic correlation for ward linkage is 0.7101180299865353.
Cophenetic correlation for weighted linkage is 0.8693784298129404.


# printing the combination of distance metric and linkage method with the highest cophenetic correlation
print(
    "Highest cophenetic correlation is {}, which is obtained with {} linkage.".format(
        high_cophenet_corr, high_dm_lm[1]
    )
)

Highest cophenetic correlation is 0.9422540609560814, which is obtained with average linkage.


# list of linkage methods
linkage_methods = ["single", "complete", "average", "centroid", "ward", "weighted"]

# lists to save results of cophenetic correlation calculation
compare_cols = ["Linkage", "Cophenetic Coefficient"]
compare = []

# to create a subplot image
fig, axs = plt.subplots(len(linkage_methods), 1, figsize=(15, 30))

# We will enumerate through the list of linkage methods above
# For each linkage method, we will plot the dendrogram and calculate the cophenetic correlation
for i, method in enumerate(linkage_methods):
    Z = linkage(subset_scaled_df, metric="euclidean", method=method)

    dendrogram(Z, ax=axs[i])
    axs[i].set_title(f"Dendrogram ({method.capitalize()} Linkage)")

    coph_corr, coph_dist = cophenet(Z, pdist(subset_scaled_df))
    axs[i].annotate(
        f"Cophenetic\nCorrelation\n{coph_corr:0.2f}",
        (0.80, 0.80),
        xycoords="axes fraction",
    )


# to create and print a dataframe to compare cophenetic correlations for different linkage methods
df_cc = pd.DataFrame(compare, columns=compare_cols)
df_cc = df_cc.sort_values(by="Cophenetic Coefficient")
df_cc


HCmodel = AgglomerativeClustering(n_clusters= 10, affinity='euclidean', linkage='average')  ## Complete the code to define the hierarchical clustering model
HCmodel.fit(hc_df)

AgglomerativeClustering(affinity='euclidean', linkage='average', n_clusters=10)

AgglomerativeClustering(affinity='euclidean', linkage='average', n_clusters=10)


subset_scaled_df["HC_Clusters"] = HCmodel.labels_
stocks1["HC_Clusters"] = HCmodel.labels_


cluster_profile = stocks1.groupby("HC_Clusters").mean()


cluster_profile["count_in_each_segments"] = (
    stocks1.groupby("HC_Clusters")["Security"].count().values
)


# to display cluster profile
cluster_profile.style.highlight_max(color="lightblue", axis=0)


# to see the names of the companies in each cluster
for cl in stocks1["HC_Clusters"].unique():
    print("In cluster {}, the following companies are present:".format(cl))
    print(stocks1[stocks1["HC_Clusters"] == cl]["Security"].unique())
    print()

In cluster 0, the following companies are present:
['American Airlines Group' 'AbbVie' 'Abbott Laboratories'
 'Adobe Systems Inc' 'Analog Devices, Inc.' 'Archer-Daniels-Midland Co'
 'Ameren Corp' 'American Electric Power' 'AFLAC Inc'
 'American International Group, Inc.' 'Apartment Investment & Mgmt'
 'Assurant Inc' 'Arthur J. Gallagher & Co.' 'Akamai Technologies Inc'
 'Albemarle Corp' 'Alaska Air Group Inc' 'Allstate Corp' 'Allegion'
 'Applied Materials Inc' 'AMETEK Inc' 'Affiliated Managers Group Inc'
 'Amgen Inc' 'Ameriprise Financial' 'American Tower Corp A'
 'AutoNation Inc' 'Anthem Inc.' 'Aon plc' 'Anadarko Petroleum Corp'
 'Amphenol Corp' 'Arconic Inc' 'Activision Blizzard'
 'AvalonBay Communities, Inc.' 'Broadcom'
 'American Water Works Company Inc' 'American Express Co' 'Boeing Company'
 'Baxter International Inc.' 'BB&T Corporation' 'Bard (C.R.) Inc.'
 'Baker Hughes Inc' 'BIOGEN IDEC Inc.' 'The Bank of New York Mellon Corp.'
 'Ball Corp' 'Bristol-Myers Squibb' 'Boston Scientific' 'BorgWarner'
 'Boston Properties' 'Caterpillar Inc.' 'Chubb Limited' 'CBRE Group'
 'Crown Castle International Corp.' 'Carnival Corp.' 'Celgene Corp.'
 'CF Industries Holdings Inc' 'Citizens Financial Group' 'Church & Dwight'
 'C. H. Robinson Worldwide' 'Charter Communications' 'CIGNA Corp.'
 'Cincinnati Financial' 'Colgate-Palmolive' 'Comerica Inc.'
 'CME Group Inc.' 'Chipotle Mexican Grill' 'Cummins Inc.' 'CMS Energy'
 'Centene Corporation' 'CenterPoint Energy' 'Capital One Financial'
 'Cabot Oil & Gas' 'The Cooper Companies' 'CSX Corp.' 'CenturyLink Inc'
 'Cognizant Technology Solutions' 'Citrix Systems' 'CVS Health'
 'Chevron Corp.' 'Concho Resources' 'Dominion Resources' 'Delta Air Lines'
 'Du Pont (E.I.)' 'Deere & Co.' 'Discover Financial Services'
 'Quest Diagnostics' 'Danaher Corp.' 'The Walt Disney Company'
 'Discovery Communications-A' 'Discovery Communications-C'
 'Delphi Automotive' 'Digital Realty Trust' 'Dun & Bradstreet'
 'Dover Corp.' 'Dr Pepper Snapple Group' 'Duke Energy' 'DaVita Inc.'
 'Devon Energy Corp.' 'eBay Inc.' 'Ecolab Inc.' 'Consolidated Edison'
 'Equifax Inc.' "Edison Int'l" 'Eastman Chemical' 'EOG Resources'
 'Equinix' 'Equity Residential' 'EQT Corporation' 'Eversource Energy'
 'Essex Property Trust, Inc.' 'E*Trade' 'Eaton Corporation'
 'Entergy Corp.' 'Edwards Lifesciences' 'Exelon Corp.' "Expeditors Int'l"
 'Expedia Inc.' 'Extra Space Storage' 'Fastenal Co'
 'Fortune Brands Home & Security' 'Freeport-McMoran Cp & Gld'
 'FirstEnergy Corp' 'Fidelity National Information Services' 'Fiserv Inc'
 'FLIR Systems' 'Fluor Corp.' 'Flowserve Corporation' 'FMC Corporation'
 'Federal Realty Investment Trust' 'First Solar Inc'
 'Frontier Communications' 'General Dynamics'
 'General Growth Properties Inc.' 'Gilead Sciences' 'Corning Inc.'
 'General Motors' 'Genuine Parts' 'Garmin Ltd.' 'Goodyear Tire & Rubber'
 'Grainger (W.W.) Inc.' 'Halliburton Co.' 'Hasbro Inc.'
 'Huntington Bancshares' 'HCA Holdings' 'Welltower Inc.' 'HCP Inc.'
 'Hess Corporation' 'Hartford Financial Svc.Gp.' 'Harley-Davidson'
 "Honeywell Int'l Inc." 'Hewlett Packard Enterprise' 'HP Inc.'
 'Hormel Foods Corp.' 'Henry Schein' 'Host Hotels & Resorts'
 'The Hershey Company' 'Humana Inc.' 'International Business Machines'
 'IDEXX Laboratories' 'Intl Flavors & Fragrances' 'International Paper'
 'Interpublic Group' 'Iron Mountain Incorporated'
 'Intuitive Surgical Inc.' 'Illinois Tool Works' 'Invesco Ltd.'
 'J. B. Hunt Transport Services' 'Jacobs Engineering Group'
 'Juniper Networks' 'Kimco Realty' 'Kimberly-Clark' 'Kinder Morgan'
 'Kansas City Southern' 'Leggett & Platt' 'Lennar Corp.'
 'Laboratory Corp. of America Holding' 'LKQ Corporation'
 'L-3 Communications Holdings' 'Lilly (Eli) & Co.' 'Lockheed Martin Corp.'
 'Alliant Energy Corp' 'Leucadia National Corp.' 'Southwest Airlines'
 'Level 3 Communications' 'LyondellBasell' 'Mastercard Inc.'
 'Mid-America Apartments' 'Macerich' "Marriott Int'l." 'Masco Corp.'
 'Mattel Inc.' "McDonald's Corp." "Moody's Corp" 'Mondelez International'
 'MetLife Inc.' 'Mohawk Industries' 'Mead Johnson' 'McCormick & Co.'
 'Martin Marietta Materials' 'Marsh & McLennan' '3M Company'
 'Monster Beverage' 'Altria Group Inc' 'The Mosaic Company'
 'Marathon Petroleum' 'Merck & Co.' 'Marathon Oil Corp.' 'M&T Bank Corp.'
 'Mettler Toledo' 'Murphy Oil' 'Mylan N.V.' 'Navient' 'Noble Energy Inc'
 'NASDAQ OMX Group' 'NextEra Energy' 'Newmont Mining Corp. (Hldg. Co.)'
 'Newfield Exploration Co' 'Nielsen Holdings'
 'National Oilwell Varco Inc.' 'Norfolk Southern Corp.'
 'Northern Trust Corp.' 'Nucor Corp.' 'Newell Brands'
 'Realty Income Corporation' 'ONEOK' 'Omnicom Group' "O'Reilly Automotive"
 'Occidental Petroleum' "People's United Financial" 'Pitney-Bowes'
 'PACCAR Inc.' 'PG&E Corp.' 'Public Serv. Enterprise Inc.' 'PepsiCo Inc.'
 'Principal Financial Group' 'Procter & Gamble' 'Progressive Corp.'
 'Pulte Homes Inc.' 'Philip Morris International' 'PNC Financial Services'
 'Pentair Ltd.' 'Pinnacle West Capital' 'PPG Industries' 'PPL Corp.'
 'Prudential Financial' 'Phillips 66' 'Quanta Services Inc.'
 'Praxair Inc.' 'PayPal' 'Ryder System' 'Royal Caribbean Cruises Ltd'
 'Regeneron' 'Robert Half International' 'Roper Industries'
 'Range Resources Corp.' 'Republic Services Inc' 'SCANA Corp'
 'Charles Schwab Corporation' 'Spectra Energy Corp.' 'Sealed Air'
 'Sherwin-Williams' 'SL Green Realty' 'Scripps Networks Interactive Inc.'
 'Southern Co.' 'Simon Property Group Inc' 'S&P Global, Inc.'
 'Stericycle Inc' 'Sempra Energy' 'SunTrust Banks' 'State Street Corp.'
 'Skyworks Solutions' 'Southwestern Energy' 'Synchrony Financial'
 'Stryker Corp.' 'Molson Coors Brewing Company' 'Teradata Corp.'
 'Tegna, Inc.' 'Torchmark Corp.' 'Thermo Fisher Scientific' 'TripAdvisor'
 'The Travelers Companies Inc.' 'Tractor Supply Company' 'Tyson Foods'
 'Tesoro Petroleum Co.' 'Total System Services' 'Texas Instruments'
 'Under Armour' 'United Continental Holdings' 'UDR Inc'
 'Universal Health Services, Inc.' 'United Health Group Inc.' 'Unum Group'
 'Union Pacific' 'United Parcel Service' 'United Technologies'
 'Varian Medical Systems' 'Valero Energy' 'Vulcan Materials'
 'Vornado Realty Trust' 'Verisk Analytics' 'Verisign Inc.'
 'Vertex Pharmaceuticals Inc' 'Ventas Inc' 'Waters Corporation'
 'Wec Energy Group Inc' 'Whirlpool Corp.' 'Waste Management Inc.'
 'Williams Cos.' 'Western Union Co' 'Weyerhaeuser Corp.'
 'Wyndham Worldwide' 'Wynn Resorts Ltd' 'Cimarex Energy' 'Xcel Energy Inc'
 'XL Capital' 'Dentsply Sirona' 'Xerox Corp.' 'Xylem Inc.' 'Yahoo Inc.'
 'Yum! Brands Inc' 'Zimmer Biomet Holdings' 'Zions Bancorp' 'Zoetis']

In cluster 5, the following companies are present:
['Alliance Data Systems']

In cluster 2, the following companies are present:
['Alexion Pharmaceuticals' 'Netflix Inc.']

In cluster 8, the following companies are present:
['Amazon.com Inc']

In cluster 7, the following companies are present:
['Apache Corporation']

In cluster 1, the following companies are present:
['Bank of America Corp' 'Intel Corp.']

In cluster 4, the following companies are present:
['Citigroup Inc.' 'Ford Motor' 'JPMorgan Chase & Co.' 'Coca Cola Company'
 'Pfizer Inc.' 'AT&T Inc' 'Verizon Communications' 'Wells Fargo'
 'Exxon Mobil Corp.']

In cluster 6, the following companies are present:
['Chesapeake Energy']

In cluster 3, the following companies are present:
['Facebook']

In cluster 9, the following companies are present:
['Priceline.com Inc']


stocks1.groupby(["HC_Clusters", "GICS Sector"])['Security'].count()

HC_Clusters  GICS Sector                
0            Consumer Discretionary         37
             Consumer Staples               18
             Energy                         27
             Financials                     45
             Health Care                    38
             Industrials                    53
             Information Technology         29
             Materials                      20
             Real Estate                    27
             Telecommunications Services     3
             Utilities                      24
1            Financials                      1
             Information Technology          1
2            Health Care                     1
             Information Technology          1
3            Information Technology          1
4            Consumer Discretionary          1
             Consumer Staples                1
             Energy                          1
             Financials                      3
             Health Care                     1
             Telecommunications Services     2
5            Information Technology          1
6            Energy                          1
7            Energy                          1
8            Consumer Discretionary          1
9            Consumer Discretionary          1
Name: Security, dtype: int64


plt.figure(figsize=(20, 20))
plt.suptitle("Boxplot of numerical variables for each cluster")

for i, variable in enumerate(num_col):
    plt.subplot(3, 4, i + 1)
    sns.boxplot(data=stocks1, x="HC_Clusters", y=variable)

plt.tight_layout(pad=2.0)

	Ticker Symbol	Security	GICS Sector	GICS Sub Industry	Current Price	Price Change	Volatility	ROE	Cash Ratio	Net Cash Flow	Net Income	Earnings Per Share	Estimated Shares Outstanding	P/E Ratio	P/B Ratio
102	DVN	Devon Energy Corp.	Energy	Oil & Gas Exploration & Production	32.000000	-15.478079	2.923698	205	70	830000000	-14454000000	-35.55	4.065823e+08	93.089287	1.785616
125	FB	Facebook	Information Technology	Internet Software & Services	104.660004	16.224320	1.320606	8	958	592000000	3669000000	1.31	2.800763e+09	79.893133	5.884467
11	AIV	Apartment Investment & Mgmt	Real Estate	REITs	40.029999	7.578608	1.163334	15	47	21818000	248710000	1.52	1.636250e+08	26.335526	-1.269332
248	PG	Procter & Gamble	Consumer Staples	Personal Products	79.410004	10.660538	0.806056	17	129	160383000	636056000	3.28	4.913916e+08	24.070121	-2.256747
238	OXY	Occidental Petroleum	Energy	Oil & Gas Exploration & Production	67.610001	0.865287	1.589520	32	64	-588000000	-7829000000	-10.23	7.652981e+08	93.089287	3.345102
336	YUM	Yum! Brands Inc	Consumer Discretionary	Restaurants	52.516175	-8.698917	1.478877	142	27	159000000	1293000000	2.97	4.353535e+08	17.682214	-3.838260
112	EQT	EQT Corporation	Energy	Oil & Gas Exploration & Production	52.130001	-21.253771	2.364883	2	201	523803000	85171000	0.56	1.520911e+08	93.089287	9.567952
147	HAL	Halliburton Co.	Energy	Oil & Gas Equipment & Services	34.040001	-5.101751	1.966062	4	189	7786000000	-671000000	-0.79	8.493671e+08	93.089287	17.345857
89	DFS	Discover Financial Services	Financials	Consumer Finance	53.619999	3.653584	1.159897	20	99	2288000000	2297000000	5.14	4.468872e+08	10.431906	-0.375934
173	IVZ	Invesco Ltd.	Financials	Asset Management & Custody Banks	33.480000	7.067477	1.580839	12	67	412000000	968100000	2.26	4.283628e+08	14.814159	4.218620

	count	unique	top	freq	mean	std	min	25%	50%	75%	max
Ticker Symbol	340	340	AAL	1	NaN	NaN	NaN	NaN	NaN	NaN	NaN
Security	340	340	American Airlines Group	1	NaN	NaN	NaN	NaN	NaN	NaN	NaN
GICS Sector	340	11	Industrials	53	NaN	NaN	NaN	NaN	NaN	NaN	NaN
GICS Sub Industry	340	104	Oil & Gas Exploration & Production	16	NaN	NaN	NaN	NaN	NaN	NaN	NaN
Current Price	340.0	NaN	NaN	NaN	80.862345	98.055086	4.5	38.555	59.705	92.880001	1274.949951
Price Change	340.0	NaN	NaN	NaN	4.078194	12.006338	-47.129693	-0.939484	4.819505	10.695493	55.051683
Volatility	340.0	NaN	NaN	NaN	1.525976	0.591798	0.733163	1.134878	1.385593	1.695549	4.580042
ROE	340.0	NaN	NaN	NaN	39.597059	96.547538	1.0	9.75	15.0	27.0	917.0
Cash Ratio	340.0	NaN	NaN	NaN	70.023529	90.421331	0.0	18.0	47.0	99.0	958.0
Net Cash Flow	340.0	NaN	NaN	NaN	55537620.588235	1946365312.175789	-11208000000.0	-193906500.0	2098000.0	169810750.0	20764000000.0
Net Income	340.0	NaN	NaN	NaN	1494384602.941176	3940150279.327936	-23528000000.0	352301250.0	707336000.0	1899000000.0	24442000000.0
Earnings Per Share	340.0	NaN	NaN	NaN	2.776662	6.587779	-61.2	1.5575	2.895	4.62	50.09
Estimated Shares Outstanding	340.0	NaN	NaN	NaN	577028337.75403	845849595.417695	27672156.86	158848216.1	309675137.8	573117457.325	6159292035.0
P/E Ratio	340.0	NaN	NaN	NaN	32.612563	44.348731	2.935451	15.044653	20.819876	31.764755	528.039074
P/B Ratio	340.0	NaN	NaN	NaN	-1.718249	13.966912	-76.119077	-4.352056	-1.06717	3.917066	129.064585

	Current Price	Price Change	Volatility	ROE	Cash Ratio	Net Cash Flow	Net Income	Earnings Per Share	Estimated Shares Outstanding	P/E Ratio	P/B Ratio	count_in_each_segment
KM_segments
0	62.644030	12.720586	1.529654	29.223404	61.319149	-156258638.297872	1919175936.170213	3.399149	636937648.906064	23.345566	0.739498	94
1	76.374133	0.834108	1.297704	23.023121	47.121387	115498173.410405	1390461699.421965	3.851069	337271215.505665	23.384698	-5.428802	173
2	46.672222	5.166566	1.079367	25.000000	58.333333	-3040666666.666667	14848444444.444445	3.435556	4564959946.222222	15.596051	-6.354193	9
3	327.006671	21.917380	2.029752	4.000000	106.000000	698240666.666667	287547000.000000	0.750000	366763235.300000	400.989188	-5.322376	3
4	108.304002	10.737770	1.165694	566.200000	26.600000	-278760000.000000	687180000.000000	1.548000	349607057.720000	34.898915	-16.851358	5
5	25.640000	11.237908	1.322355	12.500000	130.500000	16755500000.000000	13654000000.000000	3.295000	2791829362.100000	13.649696	1.508484	2
6	75.775186	14.419381	1.854929	29.111111	338.555556	696745611.111111	935969944.444444	2.005000	792523728.361111	44.919121	8.778016	18
7	508.534992	5.732177	1.504640	27.250000	150.875000	37895875.000000	1116994125.000000	15.965000	75654420.935000	43.727459	29.581664	8
8	24.485001	-13.351992	3.482611	802.000000	51.000000	-1292500000.000000	-19106500000.000000	-41.815000	519573983.250000	60.748608	1.565141	2
9	35.263847	-16.175693	2.841300	49.769231	48.153846	-135215038.461538	-2525946153.846154	-6.514231	482428533.751538	77.817252	1.618150	26

	Current Price	Price Change	Volatility	ROE	Cash Ratio	Net Cash Flow	Net Income	Earnings Per Share	Estimated Shares Outstanding	P/E Ratio	P/B Ratio	KM_segments	count_in_each_segments
HC_Clusters
0	75.812141	3.903298	1.525584	35.919003	66.775701	44288380.062305	1176573903.426791	2.889798	450041271.641277	29.469645	-2.028330	1.778816	321
1	25.640000	11.237908	1.322355	12.500000	130.500000	16755500000.000000	13654000000.000000	3.295000	2791829362.100000	13.649696	1.508484	5.000000	2
2	152.564999	16.742017	2.314435	4.000000	130.000000	380861000.000000	133320500.000000	0.485000	317332352.950000	337.464244	-9.935778	3.000000	2
3	104.660004	16.224320	1.320606	8.000000	958.000000	592000000.000000	3669000000.000000	1.310000	2800763359.000000	79.893133	5.884467	6.000000	1
4	46.672222	5.166566	1.079367	25.000000	58.333333	-3040666666.666667	14848444444.444445	3.435556	4564959946.222222	15.596051	-6.354193	2.000000	9
5	276.570007	6.189286	1.116976	30.000000	25.000000	90885000.000000	596541000.000000	8.910000	66951851.850000	31.040405	129.064585	7.000000	1
6	4.500000	-38.101788	4.559815	687.000000	22.000000	-3283000000.000000	-14685000000.000000	-22.430000	654703522.100000	28.407929	-1.840528	8.000000	1
7	44.470001	11.397804	2.405408	917.000000	80.000000	698000000.000000	-23528000000.000000	-61.200000	384444444.400000	93.089287	4.970809	8.000000	1
8	675.890015	32.268105	1.460386	4.000000	58.000000	1333000000.000000	596000000.000000	1.280000	465625000.000000	528.039074	3.904430	3.000000	1
9	1274.949951	3.190527	1.268340	29.000000	184.000000	-1671386000.000000	2551360000.000000	50.090000	50935516.070000	25.453183	-1.052429	7.000000	1

Unsupervised Learning: Trade&Ahead¶

Context¶

Objective¶

Data Dictionary¶

Importing necessary libraries and data¶

Data Overview¶

Columns:¶

Exploratory Data Analysis (EDA)¶

Univariate analysis¶

Bivariate Analysis¶

Correlation:¶

Data Preprocessing¶

Outlier Check¶

Scaling¶

K-means Clustering¶

Checking Elbow Plot¶

Silhouette Scores¶

Creating Final Model¶

Cluster Profiling¶

Hierarchical Clustering¶

Computing Cophenetic Correlation¶

Euclidean Distance Exploration¶

Checking Dendrograms¶

Creating model using sklearn¶

Cluster Profiling¶

Actionable Insights and Recommendations¶

Insights:¶